KES-FB System Research Articles

Applying Fuzzy Logic and Neural Networks to Total Hand Evaluation of Knitted Fabrics

This study of two new total hand simulating methods for knits uses fuzzy theory and neural networks. One method, a neural network system trained with a back-propaga tion algorithm, performs functional mapping between mechanical properties and the resulting total hand values of the fuzzy predicting method. The second method, a fuzzy-neural network system, uses the fuzzy membership function, weighted factor vector, and error back-propagation algorithm. The principal mechanical properties of stretchiness, bulkiness, flexibility, distortion, weight, and surface roughness of the knitted fabrics are correlated with experimentally determined Kawabata total hand values and fuzzy transformed overall hand values. Fuzzy and neural networks agree better with the subjective test results than the KES-FB system. The mechanical prop erties are fuzzified by fuzzy membership functions, then trained to predict the total hand value of outerwear knitted fabrics. In each case, the prediction error is less than the standard deviation of experimentation, and the optimum structure is investigated. These two systems, which use the Pascal programming language, produce objective ratings of outerwear knit fabrics.

Fabric-sound Classification by Autoregressive Parameters

In order to investigate the sound characteristics of fabrics, a wide range of woven fabrics was selected, and their rustling sounds were recorded. The sounds were analyzed in the forms of sound spectra through Fast Fourier Transform analysis. To evaluate the sound loudness of specimens, LPT (level pressure of total sound) values were calculated. Functions to which the autoregressive (AR) model was applied were used to describe the sound-spectra forms of specimens, and three AR parameters (ARC, ARF, and ARE) of the functions were obtained. Fabric sounds were classified into three clusters by cluster analysis of the parameters. Each of the clusters seemed to be characterized by the parameter ARC, considered to be related to sound loudness, and by the parameter ARE, affecting the over-all shape of the spectrum. To identify the mechanical properties affecting fabric-sound parameters, Kawabata's KES-FB system was used for mechanical measurement. Tensile properties, shear properties, compressional energy, thickness, and weight showed significant differences among the clusters. Of these properties, shear properties seemed to be related to the ARC parameter concerned with sound loudness. Some of the tensile properties and compressional properties were thought to be related to the spectral shapes of fabrics. Finally, shear hysteresis and compressional energy were found to be significantly discriminant for three clusters.

Predicting the Performance of Fabrics in Garment Manufacturing with Artificial Neural Networks

Neural networks are used to predict the performance of fabrics in clothing manufac turing. The predictions are based on fabric mechanical properties measured on the KES-FB system. The influence of the number of input and hidden nodes on the convergence speed and the prediction accuracy are investigated. Tests indicate that these artificial neural networks are effective for predicting potential problems in clothing manufacturing.

Antimicrobial and Blood Repellent Finishes for Cotton and Nonwoven Fabrics Based on Chitosan and Fluoropolymers

In order to impart barrier properties against microorganisms and blood to 100% cotton fabrics and 55/45% woodpulp/polyester spunlaced nonwoven fabrics, samples are treated with chitosan and fluoropolymers using the pad-dry-cure and pad-cure meth ods, respectively. Antimicrobial activity of the samples is analyzed quantitatively by measuring the number of colonies of Staphylococcus aureus. Blood repellency is as sessed with an impact penetration test using synthetic blood. Laundering durability of the finishes is measured, and scanning electron microscopy is used to evaluate changes in the fabric surfaces. To investigate the effect of finishing on the hand and air per meability of fabrics, the mechanical properties of the samples are measured by the KES-FB system. Samples treated only with chitosan show a high reduction rate in the number of colonies. Dual finished specimens treated with 1.1 % chitosan concentration also maintain over 90% reductions in the number of colonies. The blood repellency of dual finished nonwoven fabrics is superior to that of dual finished cotton. Dual finished cotton fabrics exhibited durable antimicrobial activity with repeated laundering. As regards mechanical properties, bending rigidity and shear rigidity increase when cotton and nonwoven fabrics are treated only with chitosan, but these properties decrease after the fluoropolymer treatment. Air permeability of the specimens decreases slightly after the dual finish.

Measuring and Fuzzy Predicting Total Handle from Selected Mechanical Properties of Double Weft-Knitted Fabrics

The mechanical and handle properties of three groups of double weft-knitted fabrics are measured using the KES-FB system. The double-jersey fabrics consist of double weft-knitted structures (knit, tuck, and welt stitches), and are further divided according to density and then fully relaxed. For hand measurements, seven principal physical and mechanical properties are selected (EMT, RT, RC, B, 2HG, w, MIU), which are related to four possible ways of deformation in double weft-knitted fabrics. The importance of their characteristics is deduced from a survey of a panel of thirty judges. Primary hand and total hand values from the KES-FB are analyzed and compared with our alternative simplified fuzzy total hand test result. The results from the new method for double weft-knitted fabrics provide experts with meaningful values in comparison with Ka wabata's total hand values.

Fabric Classification Based on Recognition Using a Neural Network and Dimensionality Reduction

Fabric classification plays an important role in the textile industry. In this paper, two fabric classification methods, the neural network and dimensionality reduction, are proposed to automatically classify fabrics based on measured hand properties. The methods are independent and reinforce each other. The first method adopts a neural network to recognize the category of an unknown fabric. In the second method, a dimensionality reduction technique is applied to reduce the dimensionality of the mea sured properties of input fabrics from sixteen dimensions to two. The reduced features are then plotted in a two-dimensional coordinate system to visualize and verify the classification results of the neural network. In experiments conducted to verify the validity of our proposed approach, fabric data are expressed in the form of hand prop erties extracted from the KES-FB system (Kawabata's evaluation system for fabrics). These experiments confirm the feasibility and efficiency of our approach with a wide variety of fabrics.

Fabric Handle Characteristics of Cotton Fabrics

The KES-FB system is used to evaluate the handle charactmstics of knitted, drill, plainweave and lightwight ladies cotton fabrics marketed by Pakistan.

Hand Analysis of Polyester Fabric with High-Shrinkage Fibers by KES Objective Evaluation Method

In order to get more wool-like polyester weave in the point of fabric hand, the best design of polyester weave with high-shrinkage fibers was investigated using variance analysis in orthogonal array. The effect of yarn structure and yarn density were inspected. 16 fabrics of 2/2-twill gaberdine were produced and their mechanical properties were measured using KES-FB system. Primary hand values and total hand value (THV) were calculated by conversion equations developed by Kawabata and Niwa. It was shown that THV became the highest when the high-shrinkage polyester fibers were used as weft yarns with high density and regular polyester fibers were used as warp yarns with low density. It was proved that wool-like fabric hand could be achieved by polyester weave using adequate combination of high-shrinkage polyester fibers. The subjective evaluations of fabric quality in the point of THV by experts in laboratory and factory at Shanghai did not agree with each other, but the evaluations by consumers at Shanghai agreed well with those by Japanese experts.

An Alternative Approach to the Objective Measurement of Fabrics

Objective measurements of fabric mechanical properties have great potential for quality control of clothing materials. However, access to the requisite instruments still remains a problem for many potential users due to their high cost. Therefore, a scheme for measuring all the relevant property parameters on an Instron is proposed in this article. Also, in view of the lengthy measurement process typically required by the Kawabata KES-FB system, this work provides a theoretical approach for selecting the pertinent parameters from those of the KES-FB system, so that measurement time and complexity of further data analysis can be reduced. As to the overall evaluation of fabric performance or utilization of acquired results, a graphical technique using circular diagrams is proposed to "fingerprint" or characterize fabrics. Data obtained on selected fabrics of different fiber types, weave construction, and fabric thickness are presented to illustrate this method and its applications.

The Effect of Fibre Cross-sectional Shape on Fabric Mechanical Properties and Handle

In order to clarify the effects of different fibre cross-sectional shapes on fabric mechanical properties and handle, polyester ‘Shingosen’ fabrics of different fibre cross-sections were investigated using the KES-FB system. The results were discussed by comparing them with typical women's fine dress fabrics and the following conclusions were obtained. Polyester fabric becomes soft and deformable with an increase in the space ratio in the fibre cross-section, however, it does become inelastic and unrecoverable. FUKURAMI (fullness and softness) and SHINAYAKASA (flexibility with a soft feel) of polyester fabrics is greater with higher space ratios, but, KOSHI (stiffness) and HARI (and-drape stiffness), however, is lowered. Fabric bending rigidity is in proportion to fibre bending rigidity if all other conditions such as yarn density, count and finishing conditions remain the same. However, in general, the fabric mechanical properties and handle are controlled by the fibre assembly structure rather than fibre cross-sectional shape.

Features of Mechanical Properties and Fabric Handle of Silk Weaves

Basic mechanical properties such as tensile, bending, shearing, compressional, and surface properties of each classified silk weave were measured by the KES-FB system, and fabric handle was obtained by the objective-evaluation method developed by Kawabata and Niwa. These values were examined and compared with those of typical thin dress fabrics. The discriminant analysis was used to distinguish each silk group clearly by primary hand values. The main features of fabric handle of each classified silk weave are as follows. Silk Habutae has high KOSHI and KISHIMI and low SHARI. Silk Dechine shows high SHINAYAKASA and low HARI. Silk Georgette has good SHINAYAKASA, but poor HARI and FUKURAML. Silk Fujiginu has a slightly high KISHIMI and a slightly low SHARI. High KOSHI and HARI with low SHINAYAKASA are distinctive features of silk Chirimen. Silk Shantung has higher KOSHI and HARI and lower SHINAYAKASA.

Changes in the Mechanical Properties and Fabric Handle of Polyester-fibre Fabrics Through the Finishing Stages

The basic mechanical properties and fabric handle of the polyester-fibre fabric called ‘Shingosen’ were pursued through the finishing stages by an objective-evaluation method developed by Kawabata and Niwa, using the KES-FB system. The effects of the finishing stages were clarified as follows. The polyester-fibre fabric is remarkably softened in all its mechanical properties and fabric handle by the stage of relaxing, which includes desizing, shrinking of fibres, and relaxing of the internal residual stress of the fabric. The polyester-fibre fabric becomes increasingly soft at the following weight-reduction stage because of the ‘effective gap’ between fibres and/or yarns and the splitting of fibres. However, the effects of dyeing and raising are small. By using discriminant analysis with the primary hand values as variables, it is considered that bere is a distinctive zone of fabric handle for silk-like and peach-skin-type polyester-fibre ‘Shingosen’ fabric.

Durability of Hand in Spandex Blend Fabrics

The durability of hand in spandex blend fabrics (1% spandex-wool and 2% spandex-wool/pe blends) was evaluated by the wear test and the laboratory simulation test, using an objective evaluation method of fabric handle based on the mechanical properties measured by the kes-fb system. The simulation test was performed to simulate the fabric fatigue process in actual wear by means of the kes-f5 fatigue test machine and commercial dry-cleaning. From the wear test, the primary hand values of numeri (smoothness) and fukurami (softness and fullness) showed a greater decrease for the spandex blend fabrics than those for the worsted fabrics. From the simulation test, the total and primary hand values of numeri for the spandex blend fabrics decreased remarkably compared with those for the conventional fabrics. The surface abrasion of the spandex blend fabrics caused by the wear test was much greater than that of the worsted fabrics, and was confirmed by the simulation test results. From the changes in the mechanical properties caused by the simulation test, spandex blend fabrics appear to show extensive bagging, whereas wrinkle resistance is stronger than that of the conventional fabrics. The cross-sectional areas of the spandex-wool/pe blend core spun yarns increased significantly with the simulation test, with a comparable decrease of resilience in the tensile properties, in contrast with the worsted yarns. The structural modifications in fiber assemblies of the core spun yarns govern the increase in hysteresis components of both the fabric and yarn, and the degradation of fibers in the core spun yarns contributes to the deterioration of the spandex blend fabrics.